Skip to content

Commit d8dc31f

Browse files
Release v1.2.0 (#2912)
* release prep * changelog
1 parent c564494 commit d8dc31f

File tree

5 files changed

+293
-3
lines changed

5 files changed

+293
-3
lines changed

README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -13,7 +13,7 @@ We strive to provide a broad library of time series algorithms including the
1313
latest advances, offer efficient implementations using numba, and interfaces with other
1414
time series packages to provide a single framework for algorithm comparison.
1515

16-
The latest `aeon` release is `v1.1.0`. You can view the full changelog
16+
The latest `aeon` release is `v1.2.0`. You can view the full changelog
1717
[here](https://www.aeon-toolkit.org/en/stable/changelog.html).
1818

1919
Our webpage and documentation is available at https://aeon-toolkit.org.

aeon/__init__.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,3 @@
11
"""aeon toolkit."""
22

3-
__version__ = "1.1.0"
3+
__version__ = "1.2.0"

docs/changelog.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -9,6 +9,7 @@ To stay up to date with aeon releases, subscribe to aeon
99
[here](https://libraries.io/pypi/aeon) or follow us on
1010
[Twitter](https://twitter.com/aeon_toolbox).
1111

12+
- [Version 1.2.0](changelogs/v1.2.md)
1213
- [Version 1.1.0](changelogs/v1.1.md)
1314
- [Version 1.0.0](changelogs/v1.0.md)
1415
- [Version 0.11.1](changelogs/v0/v0.11.md)

docs/changelogs/v1.2.md

Lines changed: 289 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,289 @@
1+
# v1.2.0
2+
3+
June 2025
4+
5+
## Highlights
6+
7+
- `aeon` v1.2.0 drops support for Python 3.9, Python 3.10-3.13 are the current supported versions.
8+
- Framework for whole-series anomaly detection has been implemented, and the module has been refactored
9+
into `anomaly_detection.collection` and `anomaly_detection.series` submodules.
10+
- `ProximityForect` and `ProximityTree` classifiers have been improved to support
11+
unequal length and multivariate series. The classifiers are also significantly faster.
12+
- The forecasting module has been enhanced with additional methods for direct and recursive forecasting,
13+
as well as new algorithms such as ETS. This module is still in early development, and we expect
14+
framework changes in future releases.
15+
- The similarity search module has been significantly reworked to fit the `aeon` style
16+
framework seen in other modules. See the module examples and documentation for more details.
17+
- The start of a sub-package for self suprervised learning has been added in
18+
`aeon.transformations.collection.self_supervised`, starting with the `TRILITE` algorithm.
19+
20+
## Anomaly Detection
21+
22+
### Deprecation
23+
24+
- [DEP] Remove `prts` dependency ({pr}`2863`) {user}`MatthewMiddlehurst`
25+
26+
### Documentation
27+
28+
- [DOC] resolved the inconsistency of double ticks for the anomaly detection module #809 ({pr}`2546`) {user}`AnaghDeshpande`
29+
30+
### Enhancements
31+
32+
- [ENH] Refactor range-based metrics to restore original behavior ({pr}`2781`) {user}`SebastianSchmidl`
33+
- [ENH] add informational tags back to estimator docs ({pr}`2652`) {user}`inclinedadarsh`
34+
- [ENH] Update `_continuous.py` functions ({pr}`2822`) {user}`aryanpola`
35+
- [ENH] Whole-series anomaly detection ({pr}`2326`) {user}`MatthewMiddlehurst`
36+
- [ENH, REF] Refactored time-point based ROCKAD implementation ({pr}`2804`) {user}`pattplatt`
37+
38+
### Refactored
39+
40+
- [ENH, REF] Refactored time-point based ROCKAD implementation ({pr}`2804`) {user}`pattplatt`
41+
- [REF] Refactor Anomaly Detection Module into Submodules by Algorithm Family ({pr}`2694`) {user}`Kaustbh`
42+
43+
## Benchmarking
44+
45+
### Bug Fixes
46+
47+
- [BUG] Switch results loaders from http to https ({pr}`2883`) {user}`TonyBagnall`
48+
49+
### Enhancements
50+
51+
- [ENH] Refactor range-based metrics to restore original behavior ({pr}`2781`) {user}`SebastianSchmidl`
52+
- [ENH] Update `_continuous.py` functions ({pr}`2822`) {user}`aryanpola`
53+
54+
## Classification
55+
56+
### Bug Fixes
57+
58+
- [BUG] Better error message for Rotation Forest with no usable attributes ({pr}`2798`) {user}`MatthewMiddlehurst`
59+
60+
### Documentation
61+
62+
- [DOC] Add Raises section for invalid `weights` in KNeighborsTimeSeriesClassifier (#1766) ({pr}`2764`) {user}`SomtoOnyekwelu`
63+
- [DOC] A fix to inconsistent double tick quote for the classification.distance_based module ({pr}`2627`) {user}`Ahmed-Zahran02`
64+
- [DOC] Add RotationForest Classifier Notebook for Time Series Classification ({pr}`2592`) {user}`Kaustbh`
65+
66+
### Enhancements
67+
68+
- [ENH] Implement `load_model` function for ensemble classifiers ({pr}`2631`) {user}`inclinedadarsh`
69+
- [ENH] Use n_jobs parameter in KNeighborsTimeSeriesClassifier. ({pr}`2687`) {user}`steenrotsman`
70+
- [ENH] Implemented Tracking differentiator-based multiview dilated characteristics (TD-MVDC) Classifier ({pr}`2535`) {user}`lucifer4073`
71+
- [ENH] Multivariate and unequal PF, speed-ups and distance classifier tidy ({pr}`2872`) {user}`MatthewMiddlehurst`
72+
73+
## Clustering
74+
75+
### Bug Fixes
76+
77+
- [BUG] Fix indexing errors in kdtw of KernelKMeans ({pr}`2826`) {user}`SebastianSchmidl`
78+
79+
### Documentation
80+
81+
- [DOC] Changed SummaryClusterer's summary_stat from "percentiles" to "quantiles" ({pr}`2778`) {user}`Ramana-Raja`
82+
83+
### Enhancements
84+
85+
- [ENH] Fixes Issue Improve `_check_params` method in `kmeans.py` and `kmedoids.py` ({pr}`2682`) {user}`tanishy7777`
86+
- [ENH] Added test cases for feature based clustering ({pr}`2690`) {user}`Ramana-Raja`
87+
88+
## Datasets
89+
90+
### Bug Fixes
91+
92+
- [BUG] Fix data loader ({pr}`2810`) {user}`TonyBagnall`
93+
- [ENH] Refactor example dataset for unequal length univariate ({pr}`2859`) {user}`TonyBagnall`
94+
95+
### Enhancements
96+
97+
- [ENH] Refactor example dataset for unequal length univariate ({pr}`2859`) {user}`TonyBagnall`
98+
99+
## Distances
100+
101+
### Bug Fixes
102+
103+
- [BUG] Fix indexing errors in kdtw of KernelKMeans ({pr}`2826`) {user}`SebastianSchmidl`
104+
105+
### Enhancements
106+
107+
- [ENH] Multivariate and unequal PF, speed-ups and distance classifier tidy ({pr}`2872`) {user}`MatthewMiddlehurst`
108+
109+
## Forecasting
110+
111+
### Bug Fixes
112+
113+
- [BUG] Forecasting regressor fix and notebook ({pr}`2885`) {user}`TonyBagnall`
114+
115+
### Documentation
116+
117+
- [DOC] Regression forecaster docstring ({pr}`2837`) {user}`TonyBagnall`
118+
119+
### Enhancements
120+
121+
- [ENH] Type hints/forecasting ({pr}`2737`) {user}`Ahmed-Zahran02`
122+
- [ENH] refactor dummy forecaster to naive ({pr}`2831`) {user}`TonyBagnall`
123+
- [ENH] introduce revised version of ETS ({pr}`2834`) {user}`TonyBagnall`
124+
- [ENH] Add two forecasting tags ({pr}`2882`) {user}`TonyBagnall`
125+
- [ENH] Forecasting testing ({pr}`2891`) {user}`MatthewMiddlehurst`
126+
- [ENH] Add recursive and direct methods to forecasting base class ({pr}`2899`) {user}`TonyBagnall`
127+
- [ENH] remove horizon from ETS constructor, parametrize ETS tests ({pr}`2898`) {user}`TonyBagnall`
128+
- [ENH] enhance naive forecaster with new strategies ({pr}`2869`) {user}`TinaJin0228`
129+
130+
## Networks
131+
132+
### Bug Fixes
133+
134+
- [BUG] Fix bug of shape variable assignment in AEAttentionBiGRUNetwork ({pr}`2771`) {user}`hadifawaz1999`
135+
136+
### Enhancements
137+
138+
- [ENH] Adapt the DCNN Networks to use Weight Norm Wrappers ({pr}`2628`) {user}`aadya940`
139+
- [ENH] Test coverage for AEAttentionBiGRUNetwork Improved ({pr}`2540`) {user}`lucifer4073`
140+
- [ENH] Added RNN in networks ({pr}`2875`) {user}`lucifer4073`
141+
142+
## Regression
143+
144+
### Bug Fixes
145+
146+
- [BUG] Better error message for Rotation Forest with no usable attributes ({pr}`2798`) {user}`MatthewMiddlehurst`
147+
148+
### Documentation
149+
150+
- [DOC] Docstring improved for dummy regressor ({pr}`2839`) {user}`lucifer4073`
151+
152+
### Enhancements
153+
154+
- [ENH] Add type hints for deep learning regression classes ({pr}`2644`) {user}`saadaltohamy`
155+
156+
## Segmentation
157+
158+
### Bug Fixes
159+
160+
- [BUG] Fix a bug in ClaSP Series Transformer when using floatXX as Input (where XX != 64) ({pr}`2774`) {user}`patrickzib`
161+
162+
### Documentation
163+
164+
- [DOC] Inconsistent double ticks in segmentation package, public docstring only ({pr}`2622`) {user}`nMaax`
165+
- [DOC] Improved Hidalgo Segmentation Notebook ({pr}`2616`) {user}`kavya-r30`
166+
167+
### Maintenance
168+
169+
- [MNT] stop segmenters changing state in predict ({pr}`2526`) {user}`TonyBagnall`
170+
171+
## Similarity Search
172+
173+
### Documentation
174+
175+
- [MNT, ENH, DOC] Rework similarity search ({pr}`2473`) {user}`baraline`
176+
- [DOC] Fix inconsistent double backticks in similarity_search module (#809) ({pr}`2618`) {user}`adityagh006`
177+
178+
### Enhancements
179+
180+
- [MNT, ENH, DOC] Rework similarity search ({pr}`2473`) {user}`baraline`
181+
182+
### Maintenance
183+
184+
- [MNT, ENH, DOC] Rework similarity search ({pr}`2473`) {user}`baraline`
185+
186+
## Transformations
187+
188+
### Bug Fixes
189+
190+
- [BUG] Remove typing from numba functions ({pr}`2858`) {user}`TonyBagnall`
191+
- [BUG] Fixes a bug with SFAFast throwing an error when calling transform after fit ({pr}`2897`) {user}`patrickzib`
192+
193+
### Enhancements
194+
195+
- [ENH] Optimize QUANTTransformer by using shape calculation in _fit method to avoid unnecessary computations ({pr}`2727`) {user}`shinymack`
196+
- [ENH] Add missing checks to base transformers and tidy ({pr}`2773`) {user}`MatthewMiddlehurst`
197+
- [ENH] HydraTransformer Output changed ({pr}`2656`) {user}`lucifer4073`
198+
- [ENH] add a difference transformer to series transformations ({pr}`2729`) {user}`TinaJin0228`
199+
- [ENH] Starting Self Supervised Model with first example ({pr}`2385`) {user}`hadifawaz1999`
200+
- [ENH] Series transformer pipeline and datatype list tidy ({pr}`2830`) {user}`MatthewMiddlehurst`
201+
- [ENH,REF] Unequal length collection transforms ({pr}`2903`) {user}`MatthewMiddlehurst`
202+
203+
### Refactored
204+
205+
- [REF] Refactor smoothing transformers into a sub-package ({pr}`2783`) {user}`MatthewMiddlehurst`
206+
- [ENH,REF] Unequal length collection transforms ({pr}`2903`) {user}`MatthewMiddlehurst`
207+
208+
## Unit Testing
209+
210+
### Bug Fixes
211+
212+
- [BUG] Adds test case for using csr_matrix with pickle - invalidates #2210 ({pr}`2843`) {user}`patrickzib`
213+
214+
### Documentation
215+
216+
- [DOC] Fix Broken [Source] Link and Improve Documentation for suppress_output() ({pr}`2677`) {user}`Kaustbh`
217+
218+
### Enhancements
219+
220+
- [ENH] Forecasting testing ({pr}`2891`) {user}`MatthewMiddlehurst`
221+
222+
### Maintenance
223+
224+
- [MNT] stop segmenters changing state in predict ({pr}`2526`) {user}`TonyBagnall`
225+
- [MNT] Drop Python 3.9 ({pr}`2845`) {user}`MatthewMiddlehurst`
226+
- [MNT] Fixing CI issues and separate doctests from regular CI runners ({pr}`2902`) {user}`MatthewMiddlehurst`
227+
228+
## Visualisations
229+
230+
### Maintenance
231+
232+
- [MNT] stop segmenters changing state in predict ({pr}`2526`) {user}`TonyBagnall`
233+
234+
## Other
235+
236+
### Documentation
237+
238+
- [DOC] Add implementation references ({pr}`2748`) {user}`MatthewMiddlehurst`
239+
- [DOC] Documentation improvement of BaseSeriesEstimator and BaseAeonEstimator ({pr}`2612`) {user}`kevinzb56`
240+
- [DOC,MNT] Add supporting devs to webpage and consolidate maintenance workflows ({pr}`2797`) {user}`MatthewMiddlehurst`
241+
- [DOC] Update the projects lists ({pr}`2146`) {user}`TonyBagnall`
242+
243+
### Maintenance
244+
245+
- [MNT] Use GPU installs for periodic tests ({pr}`2747`) {user}`MatthewMiddlehurst`
246+
- [MNT] Lower bound keras to discard old bugged versions of early keras3 ({pr}`2808`) {user}`hadifawaz1999`
247+
- [DOC,MNT] Add supporting devs to webpage and consolidate maintenance workflows ({pr}`2797`) {user}`MatthewMiddlehurst`
248+
- [MNT] Run PR tests when merging on any branch ({pr}`2809`) {user}`MatthewMiddlehurst`
249+
- [MNT] Update Slack link ({pr}`2877`) {user}`MatthewMiddlehurst`
250+
- [MNT] PR open bot comment changes ({pr}`2878`) {user}`MatthewMiddlehurst`
251+
- [MNT] codecov badge fix ({pr}`2908`) {user}`MatthewMiddlehurst`
252+
- [MNT] Fix codeowners for AD metrics ({pr}`2784`) {user}`SebastianSchmidl`
253+
254+
### Other
255+
256+
- [GOV] Supporting Developer role ({pr}`2775`) {user}`MatthewMiddlehurst`
257+
- [GOV] Remove inactive developers ({pr}`2776`) {user}`MatthewMiddlehurst`
258+
- [ENH] Correct broken source links for `set_params` and `get_params` in Aeon estimator docs ({pr}`2754`) {user}`Kaustbh`
259+
- [GOV] Use the NumFOCUS code of conduct and rename `aeon` workgroup ({pr}`2852`) {user}`MatthewMiddlehurst`
260+
261+
## Contributors
262+
263+
The following have contributed to this release through a collective 75 GitHub Pull Requests:
264+
265+
{user}`aadya940`,
266+
{user}`adityagh006`,
267+
{user}`Ahmed-Zahran02`,
268+
{user}`AnaghDeshpande`,
269+
{user}`aryanpola`,
270+
{user}`baraline`,
271+
{user}`hadifawaz1999`,
272+
{user}`inclinedadarsh`,
273+
{user}`Kaustbh`,
274+
{user}`kavya-r30`,
275+
{user}`kevinzb56`,
276+
{user}`lucifer4073`,
277+
{user}`MatthewMiddlehurst`,
278+
{user}`nMaax`,
279+
{user}`patrickzib`,
280+
{user}`pattplatt`,
281+
{user}`Ramana-Raja`,
282+
{user}`saadaltohamy`,
283+
{user}`SebastianSchmidl`,
284+
{user}`shinymack`,
285+
{user}`SomtoOnyekwelu`,
286+
{user}`steenrotsman`,
287+
{user}`tanishy7777`,
288+
{user}`TinaJin0228`,
289+
{user}`TonyBagnall`

pyproject.toml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
44

55
[project]
66
name = "aeon"
7-
version = "1.1.0"
7+
version = "1.2.0"
88
description = "A toolkit for machine learning from time series"
99
authors = [
1010
{name = "aeon developers", email = "contact@aeon-toolkit.org"},

0 commit comments

Comments
 (0)